Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4486 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3678. Min Range: -7.3678
Max Act: 7.3678. Min Act: -0.1700
Data Index: 1348676 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3678. Min Range: -7.3678
Max Act: 7.2428. Min Act: -0.1700
Data Index: 3174181 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.9928. Min Act: -0.1700
Data Index: 1356855 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.9303. Min Act: -0.1700
Data Index: 1278487 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.9303. Min Act: -0.1700
Data Index: 3842781 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.8053. Min Act: -0.1700
Data Index: 4900931 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.7428. Min Act: -0.1700
Data Index: 7262031 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.6803. Min Act: -0.1700
Data Index: 8400904 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.6803. Min Act: -0.1700
Data Index: 3610536 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.6491. Min Act: -0.1700
Data Index: 6966061 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.6491. Min Act: -0.1700
Data Index: 8685190 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.5866. Min Act: -0.1700
Data Index: 7340122 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.5553. Min Act: -0.1700
Data Index: 4398897 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.5553. Min Act: -0.1700
Data Index: 1146492 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.5866. Min Act: -0.1700
Data Index: 5890729 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.4928. Min Act: -0.1700
Data Index: 4930111 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.4616. Min Act: -0.1700
Data Index: 1071173 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.4303. Min Act: -0.1700
Data Index: 2579673 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.4616. Min Act: -0.1700
Data Index: 8400910 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3678. Min Range: -7.3678
Max Act: 6.3991. Min Act: -0.1700
Data Index: 395494 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19